Image-to-Video
Diffusers
text-to-video
video-to-video
image-text-to-video
audio-to-video
text-to-audio
video-to-audio
audio-to-audio
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
ltx-2
ltx-2-3
ltx-video
ltxv
lightricks
Instructions to use drbaph/LTX-2.3-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use drbaph/LTX-2.3-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("drbaph/LTX-2.3-FP8", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
fp8 lora completely broken
#1
by phazei - opened
I'm using it with LTX2.3 fp8. When I use the lora, the output is black and the audio is corrupted. I can use the original lora with no issues
we are aware of an issue with the fp8 lora and have removed it for now as we'd need a custom node in order to use it in it's current state, you can use the other two that are confirmed working with the current comfy build
drbaph changed discussion status to closed